cloudvoyant/spec
skills/spec/SKILL.md
Specification-driven development. Triggers on: "spec new", "spec go", "spec guide", "spec review", "spec refresh", "spec update", "spec clean", "spec allow", "spec help", and all legacy /spec:* trigger phrases. Unified dispatcher — pass a subcommand as the first argument.
development
Updated Jun 10, 2026
$ install --global
skillsauthnpx skillsauth add cloudvoyant/codevoyant specInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 10, 2026, 3:04 AM139.7s24 files scanned
SKILL.md
- description:
- Specification-driven development. Triggers on: "spec new", "spec go", "spec guide", "spec review", "spec refresh", "spec update", "spec clean", "spec allow", "spec help", and all legacy /spec:* trigger phrases. Unified dispatcher — pass a subcommand as the first argument.
- name:
- spec
- license:
- MIT
- compatibility:
- Designed for Claude Code. On OpenCode and VS Code Copilot, AskUserQuestion falls back to numbered list. Core functionality preserved on all platforms.
- argument-hint:
- <new|go|guide|update|review|refresh|clean|polish|help> [plan-name] [--flags]
Compatibility: AskUserQuestion falls back to numbered list on non-Claude-Code platforms.
Skill Requirements
command -v npx >/dev/null 2>&1 || echo "MISSING: npx"
Inline Usage
Pass your intent directly on the invocation line — new proceeds immediately with no opening question when a description is provided.
/spec new add OAuth login to the settings page
/spec new refactor the auth middleware to use JWT
/spec go my-plan
Critical Rules
- Never execute workflow logic here — this file only parses args and dispatches
- Step 0 always runs first — no exceptions
- Unknown verb → run
help.md— never error silently - Pass all remaining args through — workflow receives
$REMAINING_ARGSunchanged - Workflow files are authoritative — do not duplicate workflow logic in this file
- Coding agents always receive a workflow checklist — see
references/workflow-checklist.md - See
references/workflows/for per-verb behaviour; seereferences/for all templates
Step 0: Parse Arguments
VERB="[first non-flag argument, or empty]"
REMAINING_ARGS="[everything after VERB, preserving order and flags]"
# Normalise aliases
case "$VERB" in
"") VERB="help" ;;
"status") VERB="clean" ;; # /spec status → /spec clean
"list") VERB="clean" ;; # /spec list → /spec clean
"pause") VERB="clean" ;; # /spec pause → /spec clean
"stop") VERB="clean" ;; # /spec stop → /spec clean
"done") VERB="clean" ;; # /spec done → /spec clean
"delete") VERB="clean" ;; # /spec delete → /spec clean
"bg") VERB="go" ;; # /spec bg → /spec go
"run") VERB="go" ;; # /spec run → /spec go
"p") VERB="polish" ;; # /spec p → /spec polish
esac
Step 1: Dispatch to Workflow
Read and execute references/workflows/{VERB}.md, passing $REMAINING_ARGS as the argument string.
If references/workflows/{VERB}.md does not exist, fall back to references/workflows/help.md and note the unknown verb.
Workflow Index
- new (
references/workflows/new.md) — create a structured implementation plan - go (
references/workflows/go.md) — execute plan autonomously in background - guide (
references/workflows/guide.md) — guided walkthrough: step-by-step tutorial with next/skip/improvise/chat - review (
references/workflows/review.md) — review plan quality before execution - refresh (
references/workflows/refresh.md) — sync checklist status with actual progress - update (
references/workflows/update.md) — apply annotations or conversational changes - clean (
references/workflows/clean.md) — session wrap-up: stop agents, archive to docs, triage active plans (done or cancel) - polish (
references/workflows/polish.md) — strip AI-style verbosity from files touched by spec execution - allow (
references/workflows/allow.md) — pre-approve permissions for background agents - help (
references/workflows/help.md) — print command reference
Agent Index
- spec-executor (
agents/spec-executor.md) — executes plan phases autonomously; used by bg and go - spec-updater (
agents/spec-updater.md) — applies annotations and conversational plan edits; used by update - spec-planner (
agents/spec-planner.md) — researches scope and drafts multi-phase plans; used by new
Related Skills
cloudvoyant/vim
tools
VerifiedTrustedCommunity
Vim and Neovim key binding reference. Triggers on: "vim keys", "vim shortcuts", "how do I open a file in vim", "vim search replace", "vim splits", "vim buffers", "how do I navigate in vim".
SKILL.mdUpdated Jun 10, 2026
cloudvoyant/usage
testing
VerifiedTrustedCommunity
Generate a responsible-AI usage and decision-attribution report for the current session. Triggers on: "usage report", "usage generate", "usage run", "usage help".
SKILL.mdUpdated Jun 10, 2026
cloudvoyant/task
development
VerifiedTrustedCommunity
Unified task runner dispatcher: auto-detects mise, just, task.dev, or package.json scripts and provides commands to run, list, or detect the project task runner. Triggers on: "/task", "run task", "list tasks", "detect task runner", "what tasks", "mise run", "just run", "pnpm run", "package.json scripts".
SKILL.mdUpdated Jun 10, 2026
cloudvoyant/tanstack
development
VerifiedTrustedCommunity
TanStack patterns: Start file-based routing, Router v1, Query v5, Form, and server functions. Load when working with @tanstack/ packages in a React project.
SKILL.mdUpdated Jun 10, 2026